Seply splits podcast, interview, and video audio into one WAV track per speaker. Free trial, plans from $12/month. See features and pricing.
Researched and fact-checked by Bartu Cavusoglu · Updated October 26, 2026
Seply is an online audio tool that separates a spoken recording into individual, time-aligned WAV tracks, one for each detected speaker. It is aimed at podcast, interview, and video editors who want to edit, adjust, or mute each voice on its own instead of cutting clips by hand. The site states that no installation is required.
The product has two tools. Speaker Separation produces audio tracks, while Speech to Text produces a transcript with speaker labels and timestamps. Seply is clear that these outputs differ: diarization labels who spoke when, whereas separation creates actual audio files. The site lists support for more than 30 languages.
Users sign in and upload a recording: audio in WAV, MP3, M4A, AAC, or FLAC, or video in MP4 or MOV with AAC or PCM audio. Uploads can be up to 1 GB, and compatible videos upload only their original audio track without re-encoding. Seply then detects speakers automatically, or the user can enter the expected number.
After processing, the workspace lets users switch between the original mix and each isolated speaker track, then download the WAVs they need. The exact credit estimate appears before processing begins. Recordings and finished tracks are stored privately for 30 days, and credits reserved for a confirmed failed job are returned automatically.
The core feature is one independent, time-aligned WAV file per speaker, so every track starts at the same point as the original and stays in sync inside an editor. Standard mode handles conversations where people mostly take turns. Advanced Overlap is designed for interruptions and simultaneous speech, and users are expected to preview the result and decide what works for the edit.
Other capabilities include extracting just one person's voice by listening to the separated tracks and downloading only that file, a manual speaker count for tricky recordings, and a separate Speech to Text tool with speaker labels. Seply also warns that similar voices, noise, echo, and clipping can leave crosstalk, so the original should be kept.
Seply is an online audio tool that splits a spoken recording into a separate, time-aligned WAV track for each detected speaker. It is aimed at podcast, interview, and video editors. It also offers a Speech to Text tool for transcripts with speaker labels.
Monthly plans start at $12 for Starter (200 credits), then $29 for Creator (600 credits) and $65 for Studio (1,500 credits). Annual billing lowers these to $10, $24, and $54 per month. One-time credit packs cost $16, $39, and $89.
Yes. New accounts receive 20 one-time credits valid for 30 days, with no card required. That covers about 2 minutes of Standard Separation. Advanced Overlap requires a successful purchase.
Standard Separation uses 10 credits per started minute with a 10-credit minimum, so 1:00 costs 10 credits and 1:01 costs 20. Advanced Overlap uses 60 credits per started minute. Monthly credits expire 30 days after they are granted, and credit packs expire after 12 months.
Advanced Overlap is designed for interruptions and simultaneous speech. Seply says results vary with noise, echo, similar voices, and the amount of overlap, and some of the other voice may remain in a track.
Standard supports formats including WAV, MP3, M4A, AAC, FLAC, OGG, OPUS, WMA, Speex, MP4, AVI, MOV, MKV, and WebM. Advanced Overlap accepts WAV, FLAC, MP3, AAC, M4A, MP4, and MOV files up to 90 minutes. Uploads are limited to 1 GB.
No. Diarization labels who spoke when, while Seply's speaker separation creates an individual audio track for each speaker. For a transcript with speaker labels, Seply offers its separate Speech to Text tool.
For new jobs, the original recording and completed speaker tracks are stored privately for 30 days from completion. Users can listen and download during that period. Limited job metadata remains after the media expires.